An Artificial Intelligence Approach to Detect Visual Field Progression in Glaucoma Based on Spatial Pattern Analysis

Wang, Mengyu; Shen, Lucy Q.; Pasquale, Louis R.; Petrakos, Paul; Formica, Sydney; Boland, Michael V.; Wellik, Sarah R.; Moraes, Carlos Gustavo De; Myers, Jonathan S.; Saeedi, Osamah; Wang, Hui; Baniasadi, Neda; Li, Dian; Tichelaar, Jorryt; Bex, Peter J.; Elze, Tobias

doi:10.1167/iovs.18-25568

Cited by 89 publications

(66 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To focus on mild and moderate stage glaucoma, only pairs of eyes with MD equal to or better than −12 dB in both eyes were included in our data analyses. VFs with MD equal or greater than +2 dB were excluded from 42,46 (B) An example of the AT decomposition method using the total deviation (TD) plot. The plotting range is set from −38 dB to +38 dB to ensure that on the color scale white represents normal visual field sensitivities with 0 dB.…”

Section: Participant and Datamentioning

confidence: 99%

“…Each total deviation (TD) plot was decomposed into 16 archetypal patterns including one normal VF pattern and 15 defect patterns determined in our prior work, 42 which were clinically validated in a subsequent study 45 and further applied to improve glaucoma diagnosis and progression detection. 39,[46][47][48] An illustration of the 16 archetype (AT) patterns and corre-sponding nomenclature can be found in Figure 1A. An example of VF decomposition into ATs is shown in Figure 1B.…”

Section: Statistical Analysesmentioning

confidence: 99%

See 1 more Smart Citation

Inter-Eye Association of Visual Field Defects in Glaucoma and Its Clinical Utility

Teng

Choi

et al. 2020

Trans. Vis. Sci. Tech.

Self Cite

View full text Add to dashboard Cite

Section: Participant and Datamentioning

confidence: 99%

Section: Statistical Analysesmentioning

confidence: 99%

Inter-Eye Association of Visual Field Defects in Glaucoma and Its Clinical Utility

Teng

Choi

et al. 2020

Trans. Vis. Sci. Tech.

Self Cite

View full text Add to dashboard Cite

“…Several researchers, including us, have used unsupervised learning to discover (glaucomatous) patterns of VF loss [12], [13], [26]- [29]. We have extensively used Gaussian mixture modeling (GMM) to discover patterns of VF loss and to identify glaucoma progression along those GMMidentified patterns [26]- [29].…”

Section: Resultsmentioning

confidence: 99%

“…We have extensively used Gaussian mixture modeling (GMM) to discover patterns of VF loss and to identify glaucoma progression along those GMMidentified patterns [26]- [29]. Other teams have used classical AA for such goals [12], [13]. However, here we introduced a deep archetypal approach that identifies patterns of VF loss that are clinically more relevant (subjective evaluation) and patterns that may serve as signs of early glaucoma development (Fig.…”

Section: Resultsmentioning

confidence: 99%

“…Hence, any progress in predicting glaucoma early is clinically important and economically impactful. Archetypal analysis was used to identify patterns of visual field (VF) loss of patients with glaucoma [12] and then used to detect glaucoma progression from AA-identified patterns of VF loss [13]. Recent advanced in data-driven models may also aid uncovering such hidden visual functional patterns that may lead to glaucoma and hence improve our understanding of mechanisms underlying glaucoma.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Convex Representations Using Deep Archetypal Analysis for Predicting Glaucoma

Thakur

Goldbaum

Yousefi

2020

IEEE J. Transl. Eng. Health Med.

View full text Add to dashboard Cite

The purpose of this study was to identify clinically relevant patterns of glaucomatous vision loss through convex representation to predict glaucoma several years prior to disease onset. Methods: We developed a deep archetypal analysis to identify patterns of glaucomatous vision loss, and then projected visual fields over the identified patterns. Projections provided a representation that was more accurate in detecting glaucomatous vision loss, thus, more appropriate for recognizing preclinical signs of glaucoma prior to disease development. To overcome the class imbalance in prediction, we implemented a class-balanced bagging with neural networks. Results: Using original visual field as features of the class-balanced bagging classification provided an area under the receiver-operating characteristic curve (AUC) of 0.55 for predicting glaucoma approximately four years prior to disease development. Using convex representation of the visual fields as input features provided an AUC of 0.61 while using deep convex representation as input features improved the AUC to 0.71. Relevance vector machine (RVM) achieved an AUC of 0.64. Conclusion: Deep archetypal analysis representation of visual functional features with balanced bagging classification could serve as an automated tool for predicting glaucoma. Significance: Glaucoma is the second leading cause of worldwide blindness. Most people with glaucoma have no early symptoms or pain, delaying diagnosis in many patients until they reach late irreversible vision loss stages. In fact, about 50% of people with glaucoma are unaware they have the disease. Deep archetypal analysis models may impact clinical practice in effectively identifying at-risk glaucoma patients well prior to disease development.

show abstract

Glaucoma in Adults—Screening, Diagnosis, and Management

Stein

Khawaja

Weizer

2021

JAMA

392

193

View full text Add to dashboard Cite

ImportanceGlaucoma is the most common cause of irreversible blindness worldwide. Many patients with glaucoma are asymptomatic early in the disease course. Primary care clinicians should know which patients to refer to an eye care professional for a complete eye examination to check for signs of glaucoma and to determine what systemic conditions or medications can increase a patient’s risk of glaucoma. Open-angle and narrow-angle forms of glaucoma are reviewed, including a description of the pathophysiology, risk factors, screening, disease monitoring, and treatment options.ObservationsGlaucoma is a chronic progressive optic neuropathy, characterized by damage to the optic nerve and retinal nerve fiber layer, that can lead to permanent loss of peripheral or central vision. Intraocular pressure is the only known modifiable risk factor. Other important risk factors include older age, nonwhite race, and a family history of glaucoma. Several systemic medical conditions and medications including corticosteroids, anticholinergics, certain antidepressants, and topiramate may predispose patients to glaucoma. There are 2 broad categories of glaucoma, open-angle and angle-closure glaucoma. Diagnostic testing to assess for glaucoma and to monitor for disease progression includes measurement of intraocular pressure, perimetry, and optical coherence tomography. Treatment of glaucoma involves lowering intraocular pressure. This can be achieved with various classes of glaucoma medications as well as laser and incisional surgical procedures.Conclusions and RelevanceVision loss from glaucoma can be minimized by recognizing systemic conditions and medications that increase a patient’s risk of glaucoma and referring high-risk patients for a complete ophthalmologic examination. Clinicians should ensure that patients remain adherent with taking glaucoma medications and should monitor for adverse events from medical or surgical interventions used to treat glaucoma.

show abstract

An Artificial Intelligence Approach to Detect Visual Field Progression in Glaucoma Based on Spatial Pattern Analysis

Cited by 89 publications

References 54 publications

Inter-Eye Association of Visual Field Defects in Glaucoma and Its Clinical Utility

Inter-Eye Association of Visual Field Defects in Glaucoma and Its Clinical Utility

Convex Representations Using Deep Archetypal Analysis for Predicting Glaucoma

Glaucoma in Adults—Screening, Diagnosis, and Management

Contact Info

Product

Resources

About